Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1181 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.7401. Min Act: -0.0000

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.3915. Min Act: -0.0000

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.3955. Min Act: -0.0000

Data Index: 1157066 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1067596 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.2578. Min Act: -0.0000

Data Index: 116608 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.4060. Min Act: -0.0000

Data Index: 465668 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.2831. Min Act: -0.0000

Data Index: 162327 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1568687 (Python Code)

Max Activating Token Index: 508

Text #8

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1364. Min Act: -0.0000

Data Index: 458895 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1889. Min Act: -0.0000

Data Index: 589654 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1673. Min Act: -0.0000

Data Index: 112616 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1592. Min Act: -0.0000

Data Index: 998534 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1087496 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1310. Min Act: -0.0000

Data Index: 694486 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1197. Min Act: -0.0000

Data Index: 299827 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1315003 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.0742. Min Act: -0.0000

Data Index: 217050 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1100546 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1008. Min Act: -0.0000

Data Index: 755446 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.1050. Min Act: -0.0000

Data Index: 657164 (C4 (Web Text))

Max Activating Token Index: 703